Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wechat
    -0.07
    %↵↵
    -0.07
     Fraction
    -0.06
    ?>↵↵↵
    -0.06
    _encoding
    -0.06
    	animation
    -0.06
    	url
    -0.06
    .inject
    -0.06
     امکان
    -0.06
     PhoneNumber
    -0.06
    POSITIVE LOGITS
    mj
    0.07
     بال
    0.06
    ynn
    0.06
     rootNode
    0.06
     lebih
    0.06
    _todo
    0.06
     lent
    0.06
    yk
    0.06
    otto
    0.06
    yyy
    0.06
    Act Density 0.211%

    No Known Activations